Intelligent defect detection have been widely studied and applied in many industrial fields. However, intelligent tire defect inspection remains a challenging task due to tire radiographic images’ anisotropic multi-texture background in which a variety of defects may appear with intra class dissimilarity and inter class similarity. This article addresses the problem intelligent tire defect detection using end-to-end saliency detection network. A novel end-to-end residual U-structure embedded U-Net with hybrid loss function and coordinate attention module (HLU ² -Net) is proposed. In HLU ² -Net, the novel residual U-structure is used to replace encode-decode block of U-Net for fusing multiscale and multilevel features, and a hybrid loss is presented to guide defect detection for complete and clean defect mask. Moreover, a coordinate attention module is introduced to highlight useful features and weaken irrelevant features. Comparative experimental results verify that our method outperforms the state-of-the-art methods on our dataset according to six evaluation metrics. Additionally, we demonstrate that the computing efficiency of our method can meet online visual detection on tire production line.

Rapid and accurate crop chlorophyll content estimation is crucial for guiding field management and improving crop yields. This study explored the potential for potato chlorophyll content estimation based on unmanned aerial vehicle (UAV) multispectral imagery. To search the optimal estimation method, three parts of research were conducted as following. First, a combination of support vector machines (SVM) and a gaussian mixture model (GMM) thresholding method was proposed to estimate fractional vegetation cover (FVC) during the potato growing period, and the proposed method produced efficient estimates of FVC; among all the selected vegetation indices (VIs), the soil adjusted vegetation index (SAVI) had the highest accuracy. Second, the recursive feature elimination (RFE) algorithm was utilized to screen the VIs and texture features derived from multispectral images: three Vis, including modified simple ratio (MSR), ratio vegetation index (RVI) and normalized difference vegetation index (NDVI); three texture features, including correlation in the NIR band (corr-NIR), correlation in the red-edge band (corr-Red-edge) and homogeneity in the NIR band (hom-NIR), showed higher contribution to chlorophyll content estimation. Finally, a stacking model was constructed with K-Nearest Neighbor (KNN), a light gradient boosting machine (light-GBM), SVM algorithm as the base model and linear fitting as the metamodel, and four machine learning algorithms (SVM, KNN, light-GBM and stacking) were used to build the chlorophyll content estimation model suitable for different growing seasons. The results were: (1) The performance of the estimation model could be improved based on both VIs and texture features over using single-type features, and the stacking algorithm yielded the highest estimation accuracy with an R² value of 0.694 and an RMSE value of 0.553; (2) When FVC was added, the estimation model accuracy was further improved, and the stacking algorithm also produced the highest estimation accuracy with R² value of 0.739, RMSE value of 0.511 (3) When comparing modeling algorithms, stacking algorithms had greater advantages in the estimation chlorophyll content with potato plants than using single machine learning algorithms. This study indicates that taking into account the combination of VIs reflecting spectral characteristics, texture features reflecting spatial information and the FVC reflecting canopy structure properties can accomplish higher chlorophyll content estimation accuracy, and the stacking algorithm can integrate the advantages of a single machine learning model, with great potential for estimation of potato chlorophyll content.

Automatic quality control has garnered great interest from academia and industry in recent decades. Tire defect detection and classification are critical research topics for driving safety and improving yields. In this work, a novel deep convolutional sparse-coding network (DCScNet) is built for tire defect classification. In DCScNet, sparse coding is utilized to replace the convolution kernel of a convolutional neural network (CNN) for the extraction of features. Compared with CNN, it requires unsupervised training, reduces the subjectivity of artificially defined labels, and achieves higher classification accuracy. The experimental results validate its superior classification performance, compared with state-of-the-art classification algorithms. The classification accuracy reaches 96.8%, which meets industrial requirements.

Visual inspection plays a crucial role during the manufacturing of tires which are essential for safe driving. Due to complicated anisotropic multi-texture background and ambiguous defect in it, automated tire defect detection is facing huge challenges and high costs. In this study, a novel two-stage convolutional neural network (CNN) is proposed for tire inspection by combining an optimized YOLOv3 and improved pyramid scene parsing network. Comparative experiments are conducted with the-state-of-the-art to validate the effectiveness and superior performance of the proposed method. The proposed two-stage CNN method achieves an average precision of 91.39%, the defect semantic segmentation achieves a mean intersection over union of 87.86%. The average detection time for a tire is 1.158 s such that the method can be effectively implemented into the industrial workflow. It can also be easily applied to different visual inspection applications.

Automatic machine vision-based defect detection has been successfully applied to many industrial visual inspection applications. However, automatic steel surface defect detection is still a challenging task due to diverse defect categories, low-contrast between defect and complex texture background. To address these challenges, a chained atrous spatial pyramid pooling network (CASPPNet) is proposed for steel surface defect detection. In CASPPNet, chained atrous spatial pyramid pooling is designed to enlarge receptive field and obtain enrich semantic information. An improved global attention feature fusion module is introduced to achieve feature interaction and salience. Moreover, residual boundary refinement block is introduced to get more complete defect boundary. Comparative experimental results verify that our method is superior to the state-of-the-art segmentation methods on public accessible SD-saliency-900 datasets and can meet the requirement of real-time online detection (the detection efficiency is at over 47 FPS on a single GPU).

Winter jujube is a popular fresh fruit in China for its high vitamin C nutritional value and delicious taste. In terms of winter jujube object detection, in machine learning research, small size jujube fruits could not be detected with a high accuracy. Moreover, in deep learning research, due to the large model size of the network and slow detection speed, deployment in embedded devices is limited. In this study, an improved Yolov5s (You Only Look Once version 5 small model) algorithm was proposed in order to achieve quick and precise detection. In the improved Yolov5s algorithm, we decreased the model size and network parameters by reducing the backbone network size of Yolov5s to improve the detection speed. Yolov5s’s neck was replaced with slim-neck, which uses Ghost-Shuffle Convolution (GSConv) and one-time aggregation cross stage partial network module (VoV-GSCSP) to lessen computational and network complexity while maintaining adequate accuracy. Finally, knowledge distillation was used to optimize the improved Yolov5s model to increase generalization and boost overall performance. Experimental results showed that the accuracy of the optimized Yolov5s model outperformed Yolov5s in terms of occlusion and small target fruit discrimination, as well as overall performance. Compared to Yolov5s, the Precision, Recall, mAP (mean average Precision), and F₁ values of the optimized Yolov5s model were increased by 4.70%, 1.30%, 1.90%, and 2.90%, respectively. The Model size and Parameters were both reduced significantly by 86.09% and 88.77%, respectively. The experiment results prove that the model that was optimized from Yolov5s can provide a real time and high accuracy small winter jujube fruit detection method for robot harvesting.